Orders by email
Trade customers send orders as free text, PDFs and photos. Someone retypes them all.
For distributors and B2B trade
Orders in, quotes out, no retyping
Order emails, product data, quotes and trade customer questions. Turn the messy text that runs a distribution business into clean data and fast replies.
Orders parsed
emails turned into order lines
Cleaner product data
consistent titles and attributes
Faster quotes
drafted from your price list
The problem
What is slowing you down today
Messy product data
Vendor feeds arrive with inconsistent titles, units and missing attributes.
Quote turnaround
Customers buy from whoever replies first, and your reps are still building the spreadsheet.
Capabilities
Everything you need, nothing you don't
Order email parsing
Extract customer, SKU, quantity, unit and delivery date into JSON for your order system.
Product data normalisation
Standardise titles, units and attributes from vendor feeds.
Quote drafts
Draft quotes and cover emails from the pricing and terms you include.
Trade customer replies
Answers about stock, lead times and terms from the information you supply.
Idempotent batch runs
An Idempotency-Key per order means retried jobs are metered once.
Lowest-priced fit
The router sends routine extraction to the lowest-priced model with the capability.
Use cases
What teams run on it
01
Order entry automation
Order lines extracted from inbound emails for review.
02
Catalog clean-up
Consistent product records across thousands of lines.
03
Quote and follow-up emails
Fast, accurate drafts for reps to send.
04
Counter and phone support
Suggested answers for common trade questions.
How it works
From sign-up to production
- 1
Parse one order
Paste an order email into the playground and see the JSON.
- 2
Connect your ERP
Call the endpoint from your ERP or order workflow.
- 3
Scale across branches
Give each branch its own key and watch usage in the dashboard.
Control
Built so you stay in charge
Keys you control
API keys are shown once at creation and stored only as a hash. Revoke any key instantly from Settings.
Spend you can see
Every request carries its own receipt: tokens in, tokens out, latency and price. Nothing is billed that you cannot trace.
Limits you set
Per-account rate limits and a free monthly allowance keep experiments safe before they become production.
Data you decide on
You choose exactly what you send. Repeat prompts can be served from your cache, and cache hits are never billed.
For developers
One endpoint. Every model.
Send a prompt and a capability, or name a model. One bearer key, one small JSON body, and a full receipt on every response.
curl https://YOUR-DOMAIN/api/ainf/inference \
-H "Authorization: Bearer $AI_INFERENCE_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: order-1042" \
-d '{"prompt":"Summarise this ticket in one line","capability":"chat"}'Questions, answered
Will it connect to our ERP?
It is one HTTP endpoint. Your integration sends text and receives structured output.
How accurate is order extraction?
Accuracy depends on the input. Validate extracted lines against your product master before posting orders.
Can it use our price list?
Include the relevant prices and terms in the prompt. It works only from what you send.
How is it billed?
Per token at the price shown for each model, after a free monthly allowance.
Stop retyping orders
Parse your first orders on the free allowance.